{
  "_keep_in_fp32_modules": [],
  "architectures": [
    "ArgonneModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "block_size": 13568,
  "bos_token_id": null,
  "dtype": "bfloat16",
  "eos_token_id": null,
  "hidden_dropout": 0.0,
  "hidden_size": 3072,
  "interleaved_local_attention": true,
  "intermediate_size": 8192,
  "local_attention_window": 256,
  "logit_softcap": 15.0,
  "max_position_embeddings": 13568,
  "mlp_bias": false,
  "model_type": "argonne2",
  "mtp_horizon": 1,
  "mtp_loss_weight": 0.0,
  "n_embd": 3072,
  "n_head": 12,
  "n_layer": 24,
  "num_attention_heads": 12,
  "num_hidden_layers": 24,
  "num_key_value_heads": 4,
  "pad_token_id": null,
  "qk_norm": true,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sandwich_norm": true,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "5.6.2",
  "use_cache": false,
  "use_flash_attention": true,
  "use_gradient_checkpointing": false,
  "v_norm": true,
  "vocab_size": 151669,
  "z_loss_weight": 0.0,
  "torch_dtype": "bfloat16"
}